Improving Speech Emotion Recognition by Fusing Pre-trained and Acoustic Features Using Transformer and BiLSTM - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Improving Speech Emotion Recognition by Fusing Pre-trained and Acoustic Features Using Transformer and BiLSTM

Zheng Liu
  • Fonction : Auteur
  • PersonId : 1275187
Xin Kang
  • Fonction : Auteur
  • PersonId : 1275130
Fuji Ren
  • Fonction : Auteur
  • PersonId : 1275131

Résumé

With the emergence of machine learning and the deepening of human-computer interaction applications, the field of speech emotion recognition has attracted more and more attention. However, due to the high cost of speech emotion corpus construction, the speech emotion datasets are scarce. Therefore, how to obtain higher accuracy of recognition under the condition of limited corpus is one of the problems of speech emotion recognition. To solve the problem, we fused speech pre-trained features and acoustic features to enhance the generalization of speech features and proposed a novel feature fusion model based on Transformer and BiLSTM. We fused the speech pre-trained features extracted by Tera, Audio Albert, and Npc with the acoustic features of the voice, and conducted experiments on the CASIA Chinese voice emotion corpus. The results showed that our method and model achieved 94% accuracy in the Tera model.
Fichier sous embargo
Fichier sous embargo
0 7 13
Année Mois Jours
Avant la publication
mercredi 1 janvier 2025
Fichier sous embargo
mercredi 1 janvier 2025
Connectez-vous pour demander l'accès au fichier

Dates et versions

hal-04178746 , version 1 (08-08-2023)

Licence

Paternité

Identifiants

Citer

Zheng Liu, Xin Kang, Fuji Ren. Improving Speech Emotion Recognition by Fusing Pre-trained and Acoustic Features Using Transformer and BiLSTM. 12th International Conference on Intelligent Information Processing (IIP), May 2022, Qingdao, China. pp.348-357, ⟨10.1007/978-3-031-03948-5_28⟩. ⟨hal-04178746⟩
12 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More